train_mrpc_456_1760637790

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the mrpc dataset. It achieves the following results on the evaluation set:

• Loss: 0.7717
• Num Input Tokens Seen: 6002848

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 456
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.2162	2.0	1468	0.1888	600112
0.1216	4.0	2936	0.1688	1200560
0.0875	6.0	4404	0.1863	1801680
0.1421	8.0	5872	0.2793	2402912
0.0013	10.0	7340	0.4200	3002048
0.1136	12.0	8808	0.5699	3602400
0.0	14.0	10276	0.7474	4202448
0.0	16.0	11744	0.7646	4802480
0.0	18.0	13212	0.7747	5402896
0.0	20.0	14680	0.7717	6002848

Framework versions

• PEFT 0.17.1
• Transformers 4.51.3
• Pytorch 2.9.0+cu128
• Datasets 4.0.0
• Tokenizers 0.21.4